Local MCP capabilities provider for Expo
Nothing to run from here
Swt3 is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
93/100
trust score
41
downloads a day
local
runs on your machine
2k
downloads in 30d
What it does
MCP server for AI compliance audit trail and governance. 22 tools, 31 frameworks. EU AI Act, NIST AI RMF, GDPR, CMMC, ISO 42001, OWASP Agentic Top 10, SR 11-7. Witness every inference, gate tool calls, enforce clearing levels. Cryptographic attestation wi
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user swt3-mcp '--' npx -y @tenova/swt3-mcp
# 2 — ask your agent for something these tools do
# witness_inference, verify_anchor, list_procedures and 72 more
Swt3 costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
TEAll 1 server
@tenova1 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts Swt3 as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user swt3-mcp '--' npx -y @tenova/swt3-mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it asks of you
Nothing is required, but it can take SWT3_API_KEY (SWT3 API key (starts with axm_). Omit for zero-config demo mode.), SWT3_TENANT_ID (Your tenant identifier), SWT3_CONFIG_FILE (Path to swt3.yaml config file for policy-as-code), SWT3_CLEARING_LEVEL (Data clearing level: 0=analytics, 1=standard, 2=sensitive, 3=classified), SWT3_AGENT_ID (Agent identity for AI-ID.1 witnessing), SWT3_SIGNING_KEY (HMAC-SHA256 signing key for non-repudiation) if you want to set them.
What it writes
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
75 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Mint a cryptographic SWT3 witness anchor for an AI inference.
No parameter schema on file.
Verify the cryptographic integrity of an SWT3 witness anchor.
No parameter schema on file.
List available UCT (Universal Control Taxonomy) procedures from the SWT3 registry.
No parameter schema on file.
Check the current AI witness compliance posture for your tenant.
No parameter schema on file.
Get a signup link to create a free SWT3 account.
No parameter schema on file.
Witness an authorization decision as an AI-ACC.1 anchor.
No parameter schema on file.
Begin passive compliance tracking for this conversation.
No parameter schema on file.
End the audit session and produce a compliance gap report.
No parameter schema on file.
Get advisory suggestions for which SWT3 procedures to witness based on context.
No parameter schema on file.
Generate a cycle_id for a multi-agent chain.
No parameter schema on file.
Witness a handoff between agents in a multi-agent chain.
No parameter schema on file.
Voluntarily self-report a policy violation.
No parameter schema on file.
Witness model weight file integrity (AI-MDL.5).
No parameter schema on file.
Witness active LoRA/QLoRA/PEFT adapter stack (AI-MDL.6).
No parameter schema on file.
Attest the active skill/tool/plugin manifest (AI-SKILL.1).
No parameter schema on file.
Attest persistent memory sources influencing decisions (AI-SKILL.2).
No parameter schema on file.
Verify a counterpart agent's compliance posture before exchanging data or calling their tools (AI-TRUST.1).
No parameter schema on file.
Get this agent's trust credential for presentation to another agent.
No parameter schema on file.
Look up regulatory crosswalk mappings. Given a procedure ID (e.g., AI-FAIR.1),
No parameter schema on file.
Look up which regulatory frameworks apply to a jurisdiction. Given an ISO 3166-1 country code
No parameter schema on file.
Report framework coverage for the current audit session. Shows which
No parameter schema on file.
Witness a hierarchical delegation tree grant (AI-DEL.1).
No parameter schema on file.
Witness delegation boundary evaluation (AI-DEL.2).
No parameter schema on file.
Witness anchor density evaluation (AI-DENSITY.1).
No parameter schema on file.
Witness MCP security posture evaluation (AI-MCP.1).
No parameter schema on file.
Witness MCP tool integrity attestation (AI-MCP.2).
No parameter schema on file.
Witness MCP server authentication attestation (AI-MCP.3).
No parameter schema on file.
Witness MCP server discovery attestation (AI-MCP.4).
No parameter schema on file.
Witness OAuth token lifecycle event for MCP servers (AI-MCP.5).
No parameter schema on file.
Witness knowledge distillation provenance (AI-DIST.1).
No parameter schema on file.
Witness MCP elicitation consent (AI-MCP.6).
No parameter schema on file.
Witness A2A task delegation lifecycle event (AI-A2A.1).
No parameter schema on file.
Witness A2A Agent Card discovery event (AI-A2A.2).
No parameter schema on file.
Witness A2A context chain linking event (AI-A2A.3).
No parameter schema on file.
Witness model provenance chain (AI-PROV.1).
No parameter schema on file.
Witness cumulative resource consumption (AI-COST.1).
No parameter schema on file.
Witness RAG (Retrieval-Augmented Generation) context retrieval (AI-RAG.1).
No parameter schema on file.
Witness guardrail implementation and activation (AI-GRD.1).
No parameter schema on file.
Witness that human review occurred on AI-generated output (AI-HITL.1).
No parameter schema on file.
Parse and validate a .swt3-gate.yml governance gate configuration.
No parameter schema on file.
Reconstruct a forensic timeline of SWT3 witness anchors.
No parameter schema on file.
Witness data subject consent or lawful basis documentation (AI-CONSENT.1).
No parameter schema on file.
Witness output content safety classification result (AI-GRD.2).
No parameter schema on file.
Witness a safety-critical trajectory decision from a VLA or autonomous planning model (AI-MOB.6).
No parameter schema on file.
Witness incident detection and reporting (AI-INCIDENT.1).
No parameter schema on file.
Witness training data governance diligence (AI-DATA.1).
No parameter schema on file.
Witness credential scope attestation (NHI-SCOPE.1). Creates an audit trail of reported credential permissions. SWT3 is not the credential authority -- it witnesses what the IdP reports. Evidence only.
No parameter schema on file.
Witness credential lifecycle event (NHI-CYCLE.1). Records issuance, activation, suspension, expiration, or revocation. Evidence only.
No parameter schema on file.
Witness privilege change on a credential (NHI-PRIV.1). Records scope escalation or de-escalation. Evidence only.
No parameter schema on file.
Witness credential rotation (NHI-ROTATE.1). Records old-to-new credential swap with reason. Evidence only.
No parameter schema on file.
Witness agent-to-agent credential delegation (NHI-AGENT.1). Records delegation chain depth and participants. Evidence only.
No parameter schema on file.
Witness credential revocation (NHI-REVOKE.1). Records which credential was revoked, why, and whether it cascades. Evidence only.
No parameter schema on file.
Witness credential expiration event (NHI-EXPIRE.1). Records when a credential expires, whether renewal is possible, and grace period. Evidence only.
No parameter schema on file.
Witness hardware inventory attestation (HBOM-INV.1). EU CRA Art. 10(9). Evidence only.
No parameter schema on file.
Witness component lifecycle event (HBOM-LIFE.1). EU Battery Reg Art. 77. Evidence only.
No parameter schema on file.
Witness thermal profile (HBOM-THERM.1). ASHRAE TC 9.9. Evidence only.
No parameter schema on file.
Witness water consumption (HBOM-WATER.1). CSRD ESRS-E3. Evidence only.
No parameter schema on file.
Witness PUE attestation (HBOM-PUE.1). EU EED Art. 12, ISO 30134-2. Evidence only.
No parameter schema on file.
Witness hardware supply chain provenance (HBOM-SUPPLY.1). EU CRA Art. 10(9). Evidence only.
No parameter schema on file.
Witness battery State of Health (DPP-SOH.1). EU Battery Reg Art. 14(1). Evidence only.
No parameter schema on file.
Witness charge/discharge cycle (DPP-CHRG.1). EU Battery Reg Art. 14(1). Evidence only.
No parameter schema on file.
Witness battery degradation (DPP-DEGRAD.1). EU Battery Reg Art. 14(1). Evidence only.
No parameter schema on file.
Witness end-of-life handoff (DPP-EOL.1). EU Battery Reg Art. 59. Evidence only.
No parameter schema on file.
Witness demand response event (ADR-EVENT.1). FERC Order 2222. Evidence only.
No parameter schema on file.
Witness baseline consumption (ADR-BASE.1). FERC Order 2222. Evidence only.
No parameter schema on file.
Witness curtailment verification (ADR-CURT.1). FERC Order 2222. Evidence only.
No parameter schema on file.
Witness settlement data (ADR-SETTLE.1). FERC Order 2222. Evidence only.
No parameter schema on file.
Witness carbon credit / REC (ADR-CARBON.1). EU CBAM, EU RED III. Evidence only.
No parameter schema on file.
Witness grid signal correlation (ADR-GRID.1). FERC Order 2222, NERC BAL-001. Evidence only.
No parameter schema on file.
Witness orchestration topology selection (AI-ORCH.1). Records when a harness selects sequential, parallel, hierarchical, hybrid, or mesh routing for a multi-agent task. Evidence only.
No parameter schema on file.
Witness inter-agent handoff (AI-ORCH.2). Records when one agent delegates work to another with permission boundary changes. Evidence only.
No parameter schema on file.
Witness context window management (AI-CTX.1). Records when a harness truncates, summarizes, or evicts context tokens. Evidence only.
No parameter schema on file.
Witness sandbox enforcement attestation (AI-SAND.1). Records the harness's own report of tool restriction compliance. Cross-reference AI-TOOL.1 for independent verification. Evidence only.
No parameter schema on file.
Witness eval gate decision (AI-GATE.1). Records pass/fail deployment gating based on eval results. Auto-computes gate score when not provided. Evidence only.
No parameter schema on file.
Witness runtime containment attestation (AI-SHELL.1). Records that a sandboxed runtime (OpenShell, gVisor, Kata, Firecracker, WASM) enforced its containment policy. Duck-typed: no runtime SDK dependency. Evidence only.
No parameter schema on file.
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under Apache-2.0
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Swt3 or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATrust score 93 / 100
Release 0.7.7 · scanned 14 Oct 2026
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score93
Findings0 threat · 2 capability
Capabilityhigh
Coveragesource
Verificationrepo
Surface digest222a855bf6b2e853294ab93d53a3cd6117d40646b91fed7f6217b6f733c903f5
Score vectorthreat 100 → client 93
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | high | capability blast radius (high) — client exposure if the model is manipulated | −6 |
| verification-discount | repo | publisher verification (public source) — no provenance, but the source is public and inspectable | −1 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tool surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (75 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. high is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| witness_inference | state-write | state-write: declares readOnlyHint: false |
| verify_anchor | no tags | |
| list_procedures | no tags | |
| check_posture | no tags | |
| signup | no tags | |
| witness_authorization | state-write | state-write: declares readOnlyHint: false |
| start_audit_session | no tags | |
| end_audit_session | no tags | |
| suggest_procedures | no tags | |
| start_chain | no tags | |
| chain_handoff | state-write | state-write: declares readOnlyHint: false |
| report_violation | state-write | state-write: declares readOnlyHint: false |
| witness_model_integrity | state-write | state-write: declares readOnlyHint: false |
| witness_adapter_stack | state-write | state-write: declares readOnlyHint: false |
| attest_skill_manifest | state-write | state-write: declares readOnlyHint: false |
| attest_memory_context | state-write | state-write: declares readOnlyHint: false |
| verify_agent_trust | state-write | state-write: declares readOnlyHint: false |
| present_trust_credential | no tags | |
| resolve_crosswalk | no tags | |
| resolve_jurisdiction | no tags | |
| coverage_report | no tags | |
| witness_delegation_tree | state-write | state-write: declares readOnlyHint: false |
| witness_delegation_boundary | state-write | state-write: declares readOnlyHint: false |
| witness_anchor_density | state-write | state-write: declares readOnlyHint: false |
| witness_mcp_security | state-write | state-write: declares readOnlyHint: false |
| witness_tool_integrity | state-write | state-write: declares readOnlyHint: false |
| witness_server_auth | state-write | state-write: declares readOnlyHint: false |
| witness_server_discovery | state-write | state-write: declares readOnlyHint: false |
| witness_oauth_token_binding | state-write | state-write: declares readOnlyHint: false |
| witness_distillation | state-write | state-write: declares readOnlyHint: false |
| witness_elicitation | state-write | state-write: declares readOnlyHint: false |
| witness_task_lifecycle | state-write | state-write: declares readOnlyHint: false |
| witness_agent_card_discovery | state-write | state-write: declares readOnlyHint: false |
| witness_context_chain | state-write | state-write: declares readOnlyHint: false |
| witness_model_provenance | state-write | state-write: declares readOnlyHint: false |
| witness_resource_consumption | state-write | state-write: declares readOnlyHint: false |
| witness_rag_context | state-write | state-write: declares readOnlyHint: false |
| witness_guardrail | state-write | state-write: declares readOnlyHint: false |
| witness_human_review | state-write | state-write: declares readOnlyHint: false |
| gate_evaluate | no tags | |
| reconstruct_timeline | no tags | |
| witness_consent | state-write | state-write: declares readOnlyHint: false |
| witness_output_filter | state-write | state-write: declares readOnlyHint: false |
| witness_trajectory | state-write | state-write: declares readOnlyHint: false |
| witness_incident | state-write | state-write: declares readOnlyHint: false |
| witness_data_provenance | state-write | state-write: declares readOnlyHint: false |
| witness_nhi_scope | state-write | state-write: declares readOnlyHint: false |
| witness_nhi_lifecycle | state-write | state-write: declares readOnlyHint: false |
| witness_nhi_privilege_change | state-write | state-write: declares readOnlyHint: false |
| witness_nhi_rotation | state-write | state-write: declares readOnlyHint: false |
| witness_nhi_delegation | state-write | state-write: declares readOnlyHint: false |
| witness_nhi_revocation | state-write | state-write: declares readOnlyHint: false |
| witness_nhi_expiration | state-write | state-write: declares readOnlyHint: false |
| witness_hbom_inventory | state-write | state-write: declares readOnlyHint: false |
| witness_hbom_lifecycle | state-write | state-write: declares readOnlyHint: false |
| witness_hbom_thermal | state-write | state-write: declares readOnlyHint: false |
| witness_hbom_water | state-write | state-write: declares readOnlyHint: false |
| witness_hbom_pue | state-write | state-write: declares readOnlyHint: false |
| witness_hbom_supply | state-write | state-write: declares readOnlyHint: false |
| witness_dpp_soh | state-write | state-write: declares readOnlyHint: false |
| witness_dpp_charge | state-write | state-write: declares readOnlyHint: false |
| witness_dpp_degradation | state-write | state-write: declares readOnlyHint: false |
| witness_dpp_eol | state-write | state-write: declares readOnlyHint: false |
| witness_adr_event | state-write | state-write: declares readOnlyHint: false |
| witness_adr_baseline | state-write | state-write: declares readOnlyHint: false |
| witness_adr_curtailment | state-write | state-write: declares readOnlyHint: false |
| witness_adr_settlement | state-write | state-write: declares readOnlyHint: false |
| witness_adr_carbon | state-write | state-write: declares readOnlyHint: false |
| witness_adr_grid_signal | state-write | state-write: declares readOnlyHint: false |
| witness_orchestration_topology | state-write | state-write: declares readOnlyHint: false |
| witness_agent_handoff | state-write | state-write: declares readOnlyHint: false |
| witness_context_window | state-write | state-write: declares readOnlyHint: false |
| witness_sandbox_enforcement | state-write | state-write: declares readOnlyHint: false |
| witness_eval_gate | code-execstate-write | code-exec: keyword "eval" in tool name; state-write: declares readOnlyHint: false |
| witness_runtime_containment | state-write | state-write: declares readOnlyHint: false |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digest222a855bf6b2e853
Scanned2026-10-14
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 0.7.7. Pin a release below and the command asks for exactly that one.
0.7.7
14 Oct 2026
latestNo release note was published with this version.
0.7.6
13 Oct 2026
No release note was published with this version.
0.7.5
6 Oct 2026
No release note was published with this version.
0.7.4
29 Sep 2026
No release note was published with this version.
0.7.3
22 Sep 2026
No release note was published with this version.
0.7.2
15 Sep 2026
No release note was published with this version.
0.7.1
8 Sep 2026
No release note was published with this version.
0.7.0
undated
- The version this listing was on when mcprush began following its releases. The registry was not asked when it shipped, so this row carries no date.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish Swt3 can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.